Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _),
    -0.99
    +)$
    -0.96
    ctober
    -0.95
    𔘓
    -0.94
     rhythmic
    -0.92
    Ű
    -0.92
    élimin
    -0.91
    贋
    -0.90
    Sze
    -0.89
    瓩
    -0.89
    POSITIVE LOGITS
     these
    1.04
     instead
    0.96
    A
    0.86
     umane
    0.86
     interessanti
    0.85
    ISTRO
    0.85
    E
    0.84
    0
    0.84
     comuni
    0.84
     into
    0.84
    Act Density 0.012%

    No Known Activations